Similarity analysis and matching to support causal analysis and performance comparison
Project description
Comps brings together many machine learning and statistical methods for finding look alike entities to ease the selection and management of comparison groups in observational studies and experimental design to support causal analysis. It also provides a number of standardized aggregations that are helpful for comparing different types of metrics between groups.
Comps provides:
- Systematic API for applying and matching methods and assessing the similarity of different groups of entities based on common characteristics
- Methods for easily managing groups of entities across time to maintain the similarity between groups
All Comps package wheels distributed on PyPI are BSD 3-clause licensed.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
comps-0.0.1.dev0.tar.gz
(3.8 kB
view hashes)
Built Distribution
Close
Hashes for comps-0.0.1.dev0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 90bb3244173d9dd50fac9305ea354f6f18ae14552c5e0422667b29985f7ece90 |
|
MD5 | b60e3c3e830ee52e282975c2d6f3b853 |
|
BLAKE2b-256 | 15ceb829c1d4bfc0ffc95148f74b210ee899ee90335c8b84858711d6b1b80bf2 |